Predicting the success of ensemble algorithms in the banking sector

Basit Öğe Kaydı
dc.contributor.authorDağ, Özge Hüsniye Namlı
dc.date.accessioned2021-01-08T21:51:22Z
dc.date.available2021-01-08T21:51:22Z
dc.date.issued2019
dc.departmentTAÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümüen_US
dc.descriptionWOS:000511332500001en_US
dc.description.abstractThe banking sector, like other service sector, improves in accordance with the customer's needs. Therefore, to know the needs of customers and to predict customer behaviors are very important for competition in the banking sector. Data mining uncovers relationships and hidden patterns in large data sets. Classification algorithms, one of the applications of data mining, is used very effectively in decision making. In this study, the c4.5 algorithm, a decision trees algorithm widely used in classification problems, is used in an integrated way with the ensemble machine learning methods in order to increase the efficiency of the algorithms. Data obtained via direct marketing campaigns from Portugal Banks was used to classify whether customers have term deposit accounts or not. Artificial Neural Networks and Support Vector Machines as Traditional Artificial Intelligence Methods and Bagging-C4.5 and Boosted-C.45 as ensemble-decision tree hybrid methods were used in classification. Bagging-C4.5 as ensemble-decision tree algorithm achieved more powerful classification success than other used algorithms. The ensemble-decision tree hybrid methods give better results than artificial neural networks and support vector machines as traditional artificial intelligence methods for this study.
dc.identifier.doi10.4018/IJBAN.2019100102
dc.identifier.endpage31en_US
dc.identifier.issn2334-4547
dc.identifier.issn2334-4555
dc.identifier.issue4en_US
dc.identifier.scopus2-s2.0-85072636743
dc.identifier.scopusqualityQ3
dc.identifier.startpage12en_US
dc.identifier.urihttp://doi.org/10.4018/IJBAN.2019100102
dc.identifier.urihttps://hdl.handle.net/20.500.12846/183
dc.identifier.volume6en_US
dc.identifier.wosWOS:000511332500001
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorDağ, Özge Hüsniye Namlı
dc.language.isoen
dc.publisherIgi Global
dc.relation.ispartofInternational Journal Of Business Analytics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectClassificationen_US
dc.subjectData Miningen_US
dc.subjectDecision Tree Algorithmen_US
dc.subjectEnsemble Algorithmsen_US
dc.subjectFeature Selectionen_US
dc.subjectMachine Learningen_US
dc.titlePredicting the success of ensemble algorithms in the banking sector
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
00183.pdf
Boyut:
894.79 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Endüstri Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu